Lighter but Efficient Bit-Depth Expansion Network

Lighter but Efficient Bit-Depth Expansion Network
复制标题

更轻但高效的位深度扩展网络

DOI:
10.1109/tcsvt.2020.2982505
复制
发表时间:
2021-05
影响因子:
8.4
通讯作者:
Wen Gao
Wen Gao
中科院分区:
工程技术1区
文献类型:
--
作者:
Yang Zhao;Ronggang Wang;Yuan Chen;Wei Jia;Xiaoping Liu;Wen Gao

文献摘要

参考文献

相似文献

随着显示技术的发展,位深扩展(BDE)已成为在高位深显示器上显示低位深图像和视频资源的基本过程。目前大多数BDE方法都是基于传统算法的,少数基于深度神经网络的方法仍然存在像素级细节丢失或计算成本高的问题。本文提出了一种轻量级但高效的BDE网络,通过引入剩余块中剩余块的结构,可以有效地提高浅层网络的容量。此外,该网络采用残差网络结构和扩张卷积来平衡像素级信息的保留和感受野的扩展。因此,所提出的方法也可以从非常低的比特深度的图像中完全去除显著的伪影。实验结果表明,该方法可以实现性能相当,甚至优于一些国家的最先进的方法,同时具有更轻的架构和更少的参数。
With the development of display technology, bit-depth expansion (BDE) has emerged as a basic process to display low-bit-depth image and video resources on high-bit-depth monitors. Most current BDE methods are based on traditional algorithms, and the few existing methods based on deep neural networks still suffer from loss of pixel-level details or from high computational cost. This paper proposes a lightweight but efficient BDE network that can effectively improve the capacity of shallow network by introducing a residual-block-in-residual-block structure. Furthermore, the proposed network adopts residual network architecture and dilated convolution to balance the preservation of pixel-level information and the expansion of the receptive field. Hence, the proposed method can also totally remove significant artifacts from very low-bit-depth images. Experimental results demonstrate that the proposed method can achieve performance comparable to or even better than that of some state-of-the-art methods while having much lighter architecture and fewer parameters.
DOI: --
发表时间: 2018-08
期刊: ArXiv
影响因子: --
作者:
Jiahui Yu;Yuchen Fan;Jianchao Yang;N. Xu;Zhaowen Wang;Xinchao Wang;Thomas S. Huang
通讯作者: Jiahui Yu;Yuchen Fan;Jianchao Yang;N. Xu;Zhaowen Wang;Xinchao Wang;Thomas S. Huang
DOI: 10.1109/mmsp.2017.8122213
发表时间: 2017-10
期刊: 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)
影响因子: --
作者:
Hu Hao;Yang Zhang;D. Agrafiotis;M. Naccari;M. Mrak
通讯作者: Hu Hao;Yang Zhang;D. Agrafiotis;M. Naccari;M. Mrak
DOI: 10.1109/icassp.2016.7471961
发表时间: 2016-03
期刊: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
Akira Mizuno;M. Ikebe
通讯作者: Akira Mizuno;M. Ikebe
DOI: 10.1109/tip.2011.2114356
发表时间: 2011-08
影响因子: 10.6
作者:
Xin Jin;S. Goto;K. Ngan
通讯作者: Xin Jin;S. Goto;K. Ngan
用于位深度扩展的最低有效位的深度重构
DOI: 10.1109/tip.2019.2891131
发表时间: 2019
影响因子: 10.6
作者:
Yang Zhao;Ronggang Wang;Wei Jia;Wangmeng Zuo;Xiaoping Liu;Wen Gao
通讯作者: Wen Gao